VP59.44: Machine learning to diagnose rectouterine pouch obliteration with the sliding sign on transvaginal ultrasound: a prospective study
Lists
Only you see this
Abstract
Rectouterine pouch obliteration (RPO) is a severe consequence of inflammation in the pelvis, often seen in patients with endometriosis. The sliding sign is a dynamic transvaginal ultrasound (TVS) test that can diagnose RPO. We aimed to develop a machine learning (ML) network to automatically classify the state of the RP using recorded videos depicting the sliding sign test. Two expert sonologists performed, interpreted and recorded videos of consecutive patients from Sept 2018-Apr 2020. The sliding sign was classified as positive (i.e. normal) or negative (i.e. abnormal; RPO). An ML model based on a temporal residual network was prospectively trained with a dataset of TVS videos. The ML was tested on an independent test set and its diagnostic accuracy (area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive value (PPV/NPV) was compared against the reference standard sonologist classification (positive or negative sliding sign). In a dataset consisting of 749 videos, a positive sliding sign was depicted in 646 (86.2%) videos, whereas 103 (13.8%) videos depicted a negative sliding sign. The dataset was split into training (414 videos), validation (139), and testing (196) maintaining similar positive/negative proportions. When applied to the test dataset using a threshold of 0.9, the model achieved: AUC 96.5% (95%CI, 90.8-100.0%), an accuracy of 88.8% (95%CI, 83.5-92.8%), sensitivity of 88.6% (95%CI, 83.0-92.9%), specificity of 90.0% (95%CI, 68.3-98.8%), a PPV of 98.7% (95%CI, 95.4-99.7%), and a NPV of 47.7% (95%CI, 36.8-58.2%). We developed an ML model for the prediction of the TVS-based sliding sign classification with an AUC comparable to that of two expert sonologists.
BibTeX
@inproceedings{leonardi2020vp,
author = {Mathew Leonardi and G. Macais and Jodie Avery and Catrina Panuccio and Gustavo Carneiro and M. Louise Hull and G. Condous},
title = {{VP59.44: Machine learning to diagnose rectouterine pouch obliteration with the sliding sign on transvaginal ultrasound: a prospective study}},
booktitle = {Ultrasound},
year = {2020},
doi = {10.1002/uog.23327},
}Loading related content...